vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into concedo

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	CMakeLists.txt
This commit is contained in:
Concedo 2023-04-22 23:46:14 +08:00
commit 7c60441d71
8 changed files with 481 additions and 53 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama.cpp
View file

@ -2263,7 +2263,6 @@ std::vector<std::pair<std::string, struct ggml_tensor *>>& llama_internal_get_te
// Returns the size of the state
size_t llama_get_state_size(struct llama_context * ctx) {
const size_t s_bool = sizeof(int32_t);
// we don't know size of rng until we actually serialize it. so reserve more than enough memory for its serialized state.
// for reference, std::mt19937(1337) serializes to 6701 bytes.
const size_t s_rng_size = sizeof(size_t);